Skip to content
Search
paperSeptember 2026Unreviewed

Rent-a-RAG: Embedding-Space Watermarks for Auditing Third-Party RAG

Alexandr Goultiaev Tolstokorov, Kyriakos Mouratidis, Javad Dogani, Nikolaos Laoutaris

Abstract

Third-party retrieval-augmented generation (RAG) marketplaces create a new auditing problem: data providers may license corpora to a RAG operator, yet later have no visibility into whether their documents are being reused without compensation. Auditing this misuse is difficult because the operator is non-cooperative, answers are paraphrased by the generator, and one response may combine evidence from many providers. We propose DirBucket, a provider-side semantic watermarking and black-box auditi

Categories

Cite

@misc{tolstokorov2026rentarag,
  title = {{Rent-a-RAG: Embedding-Space Watermarks for Auditing Third-Party RAG}},
  author = {Alexandr Goultiaev Tolstokorov and Kyriakos Mouratidis and Javad Dogani and Nikolaos Laoutaris},
  year = {2026},
  month = sep,
  eprint = {2609.03749},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.03749}
}